Probabilistic question answering on the Web

Web‐based search engines such as Google and NorthernLight return documents that are relevant to a user query, not answers to user questions. We have developed an architecture that augments existing search engines so that they support natural language question answering. The process entails five step...

Full description

Saved in:
Bibliographic Details
Published in:Journal of the American Society for Information Science and Technology 2005-04, Vol.56 (6), p.571-583
Main Authors: Radev, Dragomir, Fan, Weiguo, Qi, Hong, Wu, Harris, Grewal, Amardeep
Format: Article
Language:English
Subjects:
Algorithms
Exact sciences and technology
Google
Information and communication sciences
Information retrieval
Information retrieval systems
Information retrieval systems. Information and document management system
Information science. Documentation
Natural language
NorthernLight
Online information retrieval
Query formulation
Questions
Sciences and techniques of general use
Search engines
Searching
Studies
Systems development
World Wide Web
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Web‐based search engines such as Google and NorthernLight return documents that are relevant to a user query, not answers to user questions. We have developed an architecture that augments existing search engines so that they support natural language question answering. The process entails five steps: query modulation, document retrieval, passage extraction, phrase extraction, and answer ranking. In this article, we describe some probabilistic approaches to the last three of these stages. We show how our techniques apply to a number of existing search engines, and we also present results contrasting three different methods for question answering. Our algorithm, probabilistic phrase reranking (PPR), uses proximity and question type features and achieves a total reciprocal document rank of .20 on the TREC8 corpus. Our techniques have been implemented as a Web‐accessible system, called NSIR.
ISSN:1532-2882
2330-1635
1532-2890
2330-1643
DOI:10.1002/asi.20146